YOLO-IRS: Infrared Ship Detection Algorithm Based on Self-Attention Mechanism and KAN in Complex Marine Background
Infrared ship detection technology plays a crucial role in ensuring maritime transportation and navigation safety. However, infrared ship targets at sea exhibit characteristics such as multi-scale, arbitrary orientation, and dense arrangements, with imaging often influenced by complex sea–sky backgr...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/1/20 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850071778070626304 |
|---|---|
| author | Limin Guo Yuwu Wang Muran Guo Xiaohai Zhou |
| author_facet | Limin Guo Yuwu Wang Muran Guo Xiaohai Zhou |
| author_sort | Limin Guo |
| collection | DOAJ |
| description | Infrared ship detection technology plays a crucial role in ensuring maritime transportation and navigation safety. However, infrared ship targets at sea exhibit characteristics such as multi-scale, arbitrary orientation, and dense arrangements, with imaging often influenced by complex sea–sky backgrounds. These factors pose significant challenges for the fast and accurate detection of infrared ships. In this paper, we propose a new infrared ship target detection algorithm, YOLO-IRS (YOLO for infrared ship target), based on YOLOv10, which improves detection accuracy while maintaining detection speed. The model introduces the following optimizations: First, to address the difficulty of detecting weak and small targets, the Swin Transformer is introduced to extract features from infrared ship images. By utilizing a shifted window multi-head self-attention mechanism, the window field of view is expanded, enhancing the model’s ability to focus on global features during feature extraction, thereby improving small target detection. Second, the C3KAN module is designed to improve detection accuracy while also addressing issues of false positives and missed detections in complex backgrounds and dense occlusion scenarios. Finally, extensive experiments were conducted on an infrared ship dataset: compared to the baseline model YOLOv10, YOLO-IRS improves precision by 1.3%, mAP<sub>50</sub> by 0.5%, and mAP<sub>50–95</sub> by 1.7%. Compared to mainstream detection algorithms, YOLO-IRS achieves higher detection accuracy while requiring relatively fewer computational resources, verifying the superiority of the proposed algorithm and enhancing the detection performance of infrared ship targets. |
| format | Article |
| id | doaj-art-c995f65b73d64cb8ab9c186694f12c35 |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-c995f65b73d64cb8ab9c186694f12c352025-08-20T02:47:13ZengMDPI AGRemote Sensing2072-42922024-12-011712010.3390/rs17010020YOLO-IRS: Infrared Ship Detection Algorithm Based on Self-Attention Mechanism and KAN in Complex Marine BackgroundLimin Guo0Yuwu Wang1Muran Guo2Xiaohai Zhou3College of Information and Communication Engineering, Harbin Engineering University (HEU), Harbin 150001, ChinaCollege of Information and Communication Engineering, Harbin Engineering University (HEU), Harbin 150001, ChinaCollege of Information and Communication Engineering, Harbin Engineering University (HEU), Harbin 150001, ChinaCollege of Information and Communication Engineering, Harbin Engineering University (HEU), Harbin 150001, ChinaInfrared ship detection technology plays a crucial role in ensuring maritime transportation and navigation safety. However, infrared ship targets at sea exhibit characteristics such as multi-scale, arbitrary orientation, and dense arrangements, with imaging often influenced by complex sea–sky backgrounds. These factors pose significant challenges for the fast and accurate detection of infrared ships. In this paper, we propose a new infrared ship target detection algorithm, YOLO-IRS (YOLO for infrared ship target), based on YOLOv10, which improves detection accuracy while maintaining detection speed. The model introduces the following optimizations: First, to address the difficulty of detecting weak and small targets, the Swin Transformer is introduced to extract features from infrared ship images. By utilizing a shifted window multi-head self-attention mechanism, the window field of view is expanded, enhancing the model’s ability to focus on global features during feature extraction, thereby improving small target detection. Second, the C3KAN module is designed to improve detection accuracy while also addressing issues of false positives and missed detections in complex backgrounds and dense occlusion scenarios. Finally, extensive experiments were conducted on an infrared ship dataset: compared to the baseline model YOLOv10, YOLO-IRS improves precision by 1.3%, mAP<sub>50</sub> by 0.5%, and mAP<sub>50–95</sub> by 1.7%. Compared to mainstream detection algorithms, YOLO-IRS achieves higher detection accuracy while requiring relatively fewer computational resources, verifying the superiority of the proposed algorithm and enhancing the detection performance of infrared ship targets.https://www.mdpi.com/2072-4292/17/1/20infrared imagesmall object detectionself-attentionKAN |
| spellingShingle | Limin Guo Yuwu Wang Muran Guo Xiaohai Zhou YOLO-IRS: Infrared Ship Detection Algorithm Based on Self-Attention Mechanism and KAN in Complex Marine Background Remote Sensing infrared image small object detection self-attention KAN |
| title | YOLO-IRS: Infrared Ship Detection Algorithm Based on Self-Attention Mechanism and KAN in Complex Marine Background |
| title_full | YOLO-IRS: Infrared Ship Detection Algorithm Based on Self-Attention Mechanism and KAN in Complex Marine Background |
| title_fullStr | YOLO-IRS: Infrared Ship Detection Algorithm Based on Self-Attention Mechanism and KAN in Complex Marine Background |
| title_full_unstemmed | YOLO-IRS: Infrared Ship Detection Algorithm Based on Self-Attention Mechanism and KAN in Complex Marine Background |
| title_short | YOLO-IRS: Infrared Ship Detection Algorithm Based on Self-Attention Mechanism and KAN in Complex Marine Background |
| title_sort | yolo irs infrared ship detection algorithm based on self attention mechanism and kan in complex marine background |
| topic | infrared image small object detection self-attention KAN |
| url | https://www.mdpi.com/2072-4292/17/1/20 |
| work_keys_str_mv | AT liminguo yoloirsinfraredshipdetectionalgorithmbasedonselfattentionmechanismandkanincomplexmarinebackground AT yuwuwang yoloirsinfraredshipdetectionalgorithmbasedonselfattentionmechanismandkanincomplexmarinebackground AT muranguo yoloirsinfraredshipdetectionalgorithmbasedonselfattentionmechanismandkanincomplexmarinebackground AT xiaohaizhou yoloirsinfraredshipdetectionalgorithmbasedonselfattentionmechanismandkanincomplexmarinebackground |